State of Charge Estimation for Lithium-Ion Battery Based on Unscented Kalman Filter and Long Short-Term Memory Neural Network

Abstract

State of charge (SOC) estimation is the core algorithm of the battery management system. However, the commonly used model-based, data-driven, or experiment-based methods struggle to independently achieve accurate SOC estimation under different working conditions and temperatures, which affects battery performance and safety. To this end, this paper proposes an online SOC estimation method that combines the model-driven and double-data-driven approaches. The unscented Kalman filter (UKF) based on the first-order RC model is used to achieve robust SOC estimation, while the data-driven long short-term memory (LSTM) neural network is used to achieve fast SOC estimation. The former model has an excellent dynamic performance and the latter has high steady-state accuracy. The SOC estimation results are input into the SOC estimation model of series LSTM so that the stable but inaccurate SOC values estimated by UKF in the first part and the accurate but fluctuating SOC values estimated by LSTM can be correlated and corrected, achieving a fast and accurate SOC estimation under various working conditions. The estimation results show that the above method has strong robustness and high accuracy, and effectively reduces model complexity and data redundancy. In addition, the root mean square error of SOC estimation under different working conditions is controlled within 1–2.3% at 0 °C, 25 °C, and 45 °C, which is better than the traditional single-SOC estimation method.

An Improved AhI Method With Deep Learning Networks for State of Charge Estimation of Lithium-Ion Battery

“…To establish the relationship between 𝑆𝑂𝐶(𝑘), 𝐼(𝑘) and 𝑉 𝑡 (𝑘) , we employed various testing profiles to simulate charging and dis-charging procedures in different scenarios. After comparing battery datasets from the Center for Advanced Life Cycle Engineering (CALCE) battery team at the University of Maryland [8,23,30,35,41], including the Dynamic Stress Test (DST), US06, Federal Urban Dynamic Stress (FUDS), and Beijing Dynamic Stress Test (BJDST), we selected the DST profile. We chose this profile due to its periodicity and the variance in loading current data, which makes it suitable for obtaining battery data.…”

“…The datasets utilized for training and validation originate from CALCE battery team [8,23,30,35]. These datasets were obtained through testing using an INR 18650-20R battery, and their specifications can be found in Table II.…”

“…where the LSTM model was trained with CALCE DST datasets and validated for BJDST and FUDS datasets[30], the results presented in Table VII and Table VIII demonstrate that the proposed method achieves higher precision in SOC estimation.…”

“…Additionally, advanced techniques like transfer learning and model compression can be employed to mitigate the impact of increased complexity in certain scenarios. In many studies, the combined methods consist of deep learning neural networks and physical model-based method with filter design for initial SOC identification and real time estimation, respectively [28][29][30][31]40]. These approaches not only provide accurate SOC estimation but also overcome the estimation errors during the initial stages of operation.…”

State-of-Charge Estimation of Lithium-Ion Battery Based on Convolutional Neural Network Combined with Unscented Kalman Filter

“…The model-based approaches often rely on complex equivalent circuit models (ECMs) and Kalman filters (KFs) to estimate SOC online [4,13]. Common variants adopt the unscented KF (UKF) [14] or the extended KF (EKF) [15]. However, as the chemical processes internal to the battery are complex, it is difficult to establish ECMs that completely describe its internal behavior, which limits the accuracy of SOC determination.…”